Conno Christou is one of the most tracked humans alive: a Whoop on his wrist, an Oura ring cross-checking it, nearly 100 biomarkers run every year. None of it saw what came next. At 35, he was diagnosed with an aggressive non-Hodgkin's lymphoma, a cancer that strikes about one in 420,000 people.
What the founder did next is the part worth your attention: he ran his own treatment like a data problem. As reported by TechCrunch AI, he fed bloodwork, scans, wearable output, and voice-transcribed symptom journals into Claude, using it to ask sharper questions than the system handed him. He wasn't hunting for a diagnosis; he wanted better questions for his doctors.
Here's why I think this matters now: a third of American adults reach for chatbots when something feels wrong, per a March poll. Most of them do it backwards. What follows is a step-by-step playbook from someone who got it right, plus the cautions experts attach to every line of it.
*Ad
When you started out, handling your own books made sense. But the business you’re running today isn’t the one you started and if your accounting hasn’t kept pace, it’s quietly working against you.
We see it all the time: outdated financials, no clear view of what’s actually profitable and horse every week pulled away from the work that grows your business. These aren’t just bookkeeping headaches, they’re growth bottlenecks.
At BELAY, our Financial Experts integrate directly into your business handling your books, reconciling accounts, running payroll, and delivering the timely insight you need to make big decisions with confidence. Expert-level support, without the overhead of a full-time hire.
Stop guessing. Start knowing. Our readers can download BELAY’s free guide, The Small Business Guide to Outsourced Accounting.
Build the baseline before you need it
Christou had four straight years of annual bloodwork and a deep wearable history. That detail is easy to skip past. Don't.
When the lymphoma hit, he wasn't starting from a blank chart: he had a personal baseline to measure every change against. Most of us walk into a diagnosis with nothing to compare. The lesson is boring and it works, so track your normal now, while an emergency still feels far away.
Don't accept the first recommendation
His first oncologist suggested the lighter chemo regimen. The night before his first infusion, the founder went looking for a second opinion. That doctor pushed the harder regimen, moving his survival odds from about 60% to around 85%.
Sit with that gap. One conversation, twenty-five percentage points of survival. "As founders, we hold the wheel," he says.
"You don't have to follow the first advice."
What struck me here: he didn't stop at two. Over two days the patient gathered 12 opinions, calling hematologists and oncologists in the US and abroad. The vote came back 11 to 1 for the harder path, and he took it.
The insight is simple: one expert can be wrong, but a weighted consensus is hard to argue with.
How Jennifer Aniston’s LolaVie brand grew sales 40% with CTV ads
The DTC beauty category is crowded. To break through, Jennifer Aniston’s brand LolaVie, worked with Roku Ads Manager to easily set up, test, and optimize CTV ad creatives. The campaign helped drive a big lift in sales and customer growth, helping LolaVie break through in the crowded beauty category.
*Ad
Turn the experience into data
He logged everything. A symptom journal built with voice transcription, capturing every side effect, every medication, every counter-medication. His Whoop flagged the days his immune system would crater, sometimes before symptoms showed up.
Why it matters: structured records turn a chaotic mess into something a model can analyze. He narrowed his focus to three variables: sleep, nutrition, and above all, psychology. "It moves the needle more than anything," he said.
"I never asked why me. Not once. That question has no useful answer."
Then he fed it all into Claude: blood results, scan data, wearable output, journal entries. His framing is the whole lesson. It didn't replace the doctors, the creator says, but it helped him ask the right questions.
For a cancer an oncologist might see once a year, a model trained on the full medical literature beat a Google search.
Pressure-test the scary results
This is the part that sold me. His final PET scan came back unclear, and his oncologist raised radiotherapy near his heart and lungs. Then he learned the false-positive rate on these scans runs around 60%.
He fed three PET scans and an MRI into the model. It flagged thymus rebound: a known phenomenon in patients under 40 where the gland reactivates after chemo and mimics active disease. The model put the odds at about 90%.
He didn't act on that number. He went and got three more human opinions. The fourth doctor confirmed it: thymus rebound, no active disease, no radiotherapy near his heart.
The machine raised the question; the humans closed it.
The best voice models, now fully orchestrated across all channels
ElevenAgents puts full orchestration on the voice models the market builds around. Voice, text chat, transcription, and reasoning in one integrated stack, <400 milliseconds, and human-sounding. Plug in any LLM, integrate tools, A/B test, and deploy across channels. More human-like conversations, lower latency, flat $0.08 per minute.
*Ad
Where the experts pump the brakes
Not everyone is sold, and they have a point. Danielle Bitterman, clinical lead for data science and AI at Mass General Brigham, told the New York Times that general-purpose chatbots are often wrong and have not been evaluated for personalized diagnoses.
The patient agrees. The model informed his questions; the doctors made every call. That's the line you can't blur: AI is a second researcher, not the final word.
Treat it like a brilliant intern who hasn't earned signing authority yet.
Start your own baseline today by saving your latest bloodwork and scans in one folder, so you have real data ready the moment you ever need sharper questions.
If you want the full step-by-step, read the patient's complete AI playbook and see exactly how he turned his diagnosis into better questions.
Worth 10 minutes if you or someone you love is staring down a hard medical decision and wants a second opinion that holds up.
Credits to the original creator.
Quick poll
Would you feed your own medical records into an AI to question your doctor?
